Liang Ma , Jinpeng Tian , Tieling Zhang , Qinghua Guo , Chi Yung Chung
{"title":"通过半监督表征学习减少数据需求,提高电池寿命预测能力","authors":"Liang Ma , Jinpeng Tian , Tieling Zhang , Qinghua Guo , Chi Yung Chung","doi":"10.1016/j.jechem.2024.10.001","DOIUrl":null,"url":null,"abstract":"<div><div>Accurate prediction of the remaining useful life (RUL) is crucial for the design and management of lithium-ion batteries. Although various machine learning models offer promising predictions, one critical but often overlooked challenge is their demand for considerable run-to-failure data for training. Collection of such training data leads to prohibitive testing efforts as the run-to-failure tests can last for years. Here, we propose a semi-supervised representation learning method to enhance prediction accuracy by learning from data without RUL labels. Our approach builds on a sophisticated deep neural network that comprises an encoder and three decoder heads to extract time-dependent representation features from short-term battery operating data regardless of the existence of RUL labels. The approach is validated using three datasets collected from 34 batteries operating under various conditions, encompassing over 19,900 charge and discharge cycles. Our method achieves a root mean squared error (RMSE) within 25 cycles, even when only 1/50 of the training dataset is labelled, representing a reduction of 48% compared to the conventional approach. We also demonstrate the method’s robustness with varying numbers of labelled data and different weights assigned to the three decoder heads. The projection of extracted features in low space reveals that our method effectively learns degradation features from unlabelled data. Our approach highlights the promise of utilising semi-supervised learning to reduce the data demand for reliability monitoring of energy devices.</div></div>","PeriodicalId":15728,"journal":{"name":"Journal of Energy Chemistry","volume":"101 ","pages":"Pages 524-534"},"PeriodicalIF":13.1000,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Enhanced battery life prediction with reduced data demand via semi-supervised representation learning\",\"authors\":\"Liang Ma , Jinpeng Tian , Tieling Zhang , Qinghua Guo , Chi Yung Chung\",\"doi\":\"10.1016/j.jechem.2024.10.001\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Accurate prediction of the remaining useful life (RUL) is crucial for the design and management of lithium-ion batteries. Although various machine learning models offer promising predictions, one critical but often overlooked challenge is their demand for considerable run-to-failure data for training. Collection of such training data leads to prohibitive testing efforts as the run-to-failure tests can last for years. Here, we propose a semi-supervised representation learning method to enhance prediction accuracy by learning from data without RUL labels. Our approach builds on a sophisticated deep neural network that comprises an encoder and three decoder heads to extract time-dependent representation features from short-term battery operating data regardless of the existence of RUL labels. The approach is validated using three datasets collected from 34 batteries operating under various conditions, encompassing over 19,900 charge and discharge cycles. Our method achieves a root mean squared error (RMSE) within 25 cycles, even when only 1/50 of the training dataset is labelled, representing a reduction of 48% compared to the conventional approach. We also demonstrate the method’s robustness with varying numbers of labelled data and different weights assigned to the three decoder heads. The projection of extracted features in low space reveals that our method effectively learns degradation features from unlabelled data. Our approach highlights the promise of utilising semi-supervised learning to reduce the data demand for reliability monitoring of energy devices.</div></div>\",\"PeriodicalId\":15728,\"journal\":{\"name\":\"Journal of Energy Chemistry\",\"volume\":\"101 \",\"pages\":\"Pages 524-534\"},\"PeriodicalIF\":13.1000,\"publicationDate\":\"2024-10-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Energy Chemistry\",\"FirstCategoryId\":\"92\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2095495624006910\",\"RegionNum\":1,\"RegionCategory\":\"化学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"Energy\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Energy Chemistry","FirstCategoryId":"92","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2095495624006910","RegionNum":1,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"Energy","Score":null,"Total":0}
Enhanced battery life prediction with reduced data demand via semi-supervised representation learning
Accurate prediction of the remaining useful life (RUL) is crucial for the design and management of lithium-ion batteries. Although various machine learning models offer promising predictions, one critical but often overlooked challenge is their demand for considerable run-to-failure data for training. Collection of such training data leads to prohibitive testing efforts as the run-to-failure tests can last for years. Here, we propose a semi-supervised representation learning method to enhance prediction accuracy by learning from data without RUL labels. Our approach builds on a sophisticated deep neural network that comprises an encoder and three decoder heads to extract time-dependent representation features from short-term battery operating data regardless of the existence of RUL labels. The approach is validated using three datasets collected from 34 batteries operating under various conditions, encompassing over 19,900 charge and discharge cycles. Our method achieves a root mean squared error (RMSE) within 25 cycles, even when only 1/50 of the training dataset is labelled, representing a reduction of 48% compared to the conventional approach. We also demonstrate the method’s robustness with varying numbers of labelled data and different weights assigned to the three decoder heads. The projection of extracted features in low space reveals that our method effectively learns degradation features from unlabelled data. Our approach highlights the promise of utilising semi-supervised learning to reduce the data demand for reliability monitoring of energy devices.
期刊介绍:
The Journal of Energy Chemistry, the official publication of Science Press and the Dalian Institute of Chemical Physics, Chinese Academy of Sciences, serves as a platform for reporting creative research and innovative applications in energy chemistry. It mainly reports on creative researches and innovative applications of chemical conversions of fossil energy, carbon dioxide, electrochemical energy and hydrogen energy, as well as the conversions of biomass and solar energy related with chemical issues to promote academic exchanges in the field of energy chemistry and to accelerate the exploration, research and development of energy science and technologies.
This journal focuses on original research papers covering various topics within energy chemistry worldwide, including:
Optimized utilization of fossil energy
Hydrogen energy
Conversion and storage of electrochemical energy
Capture, storage, and chemical conversion of carbon dioxide
Materials and nanotechnologies for energy conversion and storage
Chemistry in biomass conversion
Chemistry in the utilization of solar energy